Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

Loading page content

© 2026 Leaderboard.cn. Traceable AI model evaluations and rankings.

About Ranking methodology Changelog

v0.1.53.364ac010a008浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

HLE (w/ Tools)AgentsReasoning

Official website

Results for 47 models collected from 20 public sources.

Ranking Sources

#ModelScore

1

GPT-5.6 SolOpenAI

64.5%

2

Claude Fable 5Anthropic

64.5%

3

GLM-5.3Zhipu AI

62.5%

4

DeepSeek-V4-Pro-0813DeepSeek

60.0%

5

Kimi K3Moonshot AI

59.8%

6

GPT-5.4 ProOpenAI

58.7%

7

Claude Opus 4.8Anthropic

57.9%

8

GPT-5.5 ProOpenAI

57.2%

9

Qwen3.8-MaxAlibaba

56.2%

10

Qwen3.8-2.4T-A95BAlibaba

56.2%

47 models total